GELİŞMİŞ SÜRÜCÜ DESTEK SİSTEMLERİ İÇİN TRAFİK İŞARETLERİNE DUYARLI YAPAY ZEKÂ MODELİ

Year 2025, Issue: Advanced Online Publication, 1 - 1

Seyfettin Vadi , Simge Koçak

https://doi.org/10.17134/khosbd.1783706

Abstract

Günümüzde robotik ve otonom sistemlerin giderek yaygınlaşması, sürüş ortamının algılanması ve sürücülere ya da otonom sistemlere gerçek zamanlı bilgi sunan Gelişmiş Sürücü Destek Sistemleri (ADAS) ile bütünleştiğinde, yol güvenliği açısından büyük bir dönüşüm sağlamaktadır. Özellikle bilgisayar teknolojilerindeki ilerlemeler ve derin öğrenme tabanlı yöntemlerin başarısı, hem insan faktöründen kaynaklanan hataları en aza indirme hem de trafiği akıcı, güvenli ve konforlu hale getirme potansiyeli taşımaktadır. Bu çalışmada, otoyollardaki trafik akışı sorunlarını, zaman kaybını ve maliyet artışlarını azaltmak amacıyla trafik işaretlerine, özellikle de trafik ışıklarına duyarlı bir yapay zekâ modeli geliştirilmiştir. Bu bağlamda çalışmada, geleneksel otomatik olay tespit (AID) yöntemlerinde sıkça karşılaşılan düşük tespit oranları ve yüksek yanlış alarm sorunlarını aşmak üzere, sinir ağları ve derin öğrenme teknikleri kullanılmıştır. Özellikle geliştirilmiş YOLOv8 algoritması kullanılarak ileri seviye nesne tespiti algoritmaları yardımıyla, trafik ışıkları da dâhil olmak üzere çeşitli yol işaretleri ve şeritler, farklı çevresel koşullar ve görüş açıları altında yüksek doğrulukla saptanmıştır. Böylece yalnızca trafik akışına yönelik veriler değil, aynı zamanda işaretlerin anlamları, konumları ve yönleri de modele entegre edilerek, sürücülere ve otonom araçlara daha kapsamlı ve güncel bilgi ortamı sunulmuştur. Sonuç olarak geliştirilen modelin, trafik yönetim merkezlerinin operasyonel verimliliğini artırması, sürücü güvenliği ve konforunu iyileştirmesi ve otonom araçların sürekli değişen sürüş ortamlarında daha etkin kararlar alması sağlanmıştır.

Keywords

ADAS , Otonom Araç , Trafik işaretlerine duyarlı sistem.

A TRAFFIC SIGN-AWARE ARTIFICIAL INTELLIGENCE MODEL FOR ADVANCED DRIVER ASSISTANCE SYSTEMS

Abstract

The increasing prevalence of robotics and autonomous systems today, when integrated with Advanced Driver Assistance Systems (ADAS) that perceive the driving environment and provide real-time information to drivers or autonomous systems, is bringing about a major transformation in terms of road safety. Specifically, advancements in computer technologies and the success of deep learning-based methods hold the potential to both minimize errors stemming from human factors and make traffic smooth, safe, and comfortable. In this study, an artificial intelligence model sensitive to traffic signs, especially traffic lights, has been developed to reduce traffic flow problems, time loss, and cost increases on highways. In this context, the study utilizes neural networks and deep learning techniques to overcome the low detection rates and high false alarm issues frequently encountered in traditional automatic incident detection (AID) methods. Advanced object detection algorithms, particularly with the enhanced YOLOv8 algorithm, have been used to accurately identify various road signs and lanes, including traffic lights, under different environmental conditions and viewing angles. Thus, not only traffic flow data but also the meanings, locations, and directions of signs were integrated into the model, providing drivers and autonomous vehicles with a more comprehensive and up-to-date information environment. As a result, the developed model is expected to increase the operational efficiency of traffic management centers, improve driver safety and comfort, and enable autonomous vehicles to make more effective decisions in constantly changing driving environments.

Keywords

ADAS , Autonomous Vehicle , Traffic Sign Recognition System.

References

• [1] WHO (World Health Organization) (2018). Global Status Report on Road Safety 2018. World Health Organization, Geneva.
• [2] Peden, M., Scurfield, R., Sleet, D., Mohan, D., Hyder, A.A., Jarawan, E., & Mathers, C. (2004). World Report on Road Traffic Injury Prevention. World Health Organization, Geneva.
• [3] European Commission (2022). EU Road Safety Policy. European Commission, Mobility and Transport.
• [4] Smiley, A., Brookhuis, K., & De Waard, D. (1987). Human Behavior and Traffic Safety. In: Evans, L. & Schwing, R.C. (Eds.), Human Behavior and Traffic Safety (pp. 51–70). Springer, Boston, MA.
• [5] Y. Zein, M. Darwiche, O. Mokhiamar, GPS tracking system for autonomous vehicles. Alexandria Engineering Journal (2018) 57, 3127–3137
• [6] Zanchin, B. C., Adamshuk, R., Santos, M. M., & Collazos, K. S. (2017, October). On the instrumentation and classification of autonomous cars. In 2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC) (pp. 2631-2636). IEEE
• [7] Wakabayashi, D. (2019). Self-Driving Uber Car Kills Pedestrian in Arizona, Where Robots Roam. Retrieved from https://www.nytimes.com/2018/03/19/technology/uber-driverlessfatality.html
• [8] Chitradevi, B., ve P. Srimathi. “An overview on image processing techniques." International Journal of Innovative Research in Computer and Communication Engineering 2.11.”(2014).
• [9] Cowan, R. S. (1987). The consumption junction: A proposal for research strategies in the sociology of technology. The social construction of technological systems: New directions in the sociology and history of technology, 26180.
• [10] Ozguner U., Acatman T. ve Redmil K., (2011), “Autonomous Ground Vehicles”, USA, Artech House, 3-5.
• [11] Pomerleau D.A., (1989), “ALVINN: An Autonomous Land Vehicle in a Neural Network”, In Advances in Neural Information Processing Systems, Morgan Kaufmann, San Mateo.
• [12] Çayıroğlu İ., Şimşir M., (2008), “PIC ve Step Motorla Sürülen Bir Mobil Robotun Uzaktan Kamera Sistemi ile Kontrolü”, Erciyes Üniversitesi Fen Bilimleri Enstitüsü Dergisi, 24(1-2), 1-16.
• [13] Fong P. E., Yusoff M. A., (2011), “Real-Time Control of Wi-Fi Surveillance Robot”, Proceeding of the International Conference on Advanced Science Engineering and Information Technology, Malasia.
• [14] Kuo G., Cheng C., Wu C., (2014), “Design and Implementation of a Remote Monitoring Cleaning Robot”, International Automatic Control Conference, Taiwan.
• [15] Espes D., Autret Y., Vareille J., Le Parc P., (2014), “Designing a Low-Cost Web-Controlled Mobile Robot for Home Monitoring”, The Eighth International Conference on Mobile Ubiquitous Computing, Systems, Services and Technologies, Italy.
• [16] Çetinkaya A., (2017), “Otonom Bir robotun bulanık kontrolör yaklaşımı ile konum kontrolü”, Karatay Üniversitesi, YL Tezi.
• [17]Ellahyani, A., Ansari, M. E., ve Jaafari, I. E. (2016). Traffic sign detection and recognition based on random forests. Applied Soft Computing, 46, 805-815.
• [18]Stallkamp, J., Schlipsing, M., Salmen, J., ve Igel, C. (2012). Man vs. Computer: Benchmarking Machine Learning Algorithms for Traffic Sign Recognition. Neural networks, 323–332.
• [19] Xu, X., Jin, J., Zhang, S., Zhang, L., Pu, S., ve Chen, Z. (2019). Smart data driven traffic sign detection method based on adaptive color threshold and shape symmetry. Future Generation Computer Systems, 94, 381-391.
• [20] Arcos-García, A., Álvarez-García, J. A., ve Soria-Morillo, L. M. (2018). Evaluation of deep neural networks for traffic sign detection systems. Neurocomputing, 316, 332-344.
• [21] Torres, L. T., Paixao, T. M., Berriel, R. F., De Souza, A. F., Badue, C., Sebe, N., ve Oliveira-Santos, T. (2019). Effortless Deep Training for Traffic Sign Detection Using Templates and Arbitrary Natural Images. International Joint Conference on Neural Networks. Budapest.
• [22] Rahman, Q. M., Sünderhauf, N., ve Dayoub, F. (2019). Did You Miss the Sign? A False Negative Alarm System for Traffic Sign Detectors. arXiv:1903.06391.
• [23] Mathias, M., Timofte, R., Benenson, R., ve Van Gool, L. (2013). Traffic sign recognition — How far are we from the solution? International Joint Conference on Neural Networks (IJCNN), (s. 1-8). Dallas.
• [24] Jung, S., Lee, U., Jung, J., ve Shim, D. H. (2016). Real-time Traffic Sign Recognition System with Deep Convolutional Neural Network. 13th International Conference on Ubiquitous Robots and Ambient Intelligence. Urai.
• [25] Li, Y., Møgelmose, A., ve Trivedi, M. M. (2016). Pushing the “Speed Limit”: HighAccuracy U.S. Traffic Sign Recognition with Convolutional Neural Networks. IEEE Transactions on Intelligent Vehicles, 167-176.
• [26] Abedin, Z., Dhar, P., Hossenand, M. K., ve Deb, K. (2017). Traffic Sign Detection and Recognition Using Fuzzy Segmentation Approach and Artificial Neural Network Classifier Respectively. International Conference on Electrical, Computer and Communication Engineering, (s. 518-523). Cox's Bazar.
• [27] Song, S., Que, Z., Hou, J., Du, S., ve Song, Y. (2019). An efficient convolutional neural network for small traffic sign detection. Journal of Systems Architecture, 97, 269-277.
• [28] Alpkıray N., (2019), “Otonom Keşif Amaçlı Robot Sistemleri İçin Geri dönüş Rotası Hesaplama Algoritması Geliştirilmesi”, Cumhuriyet Üniversitesi, YL Tezi.
• [29] Lin, P., Abney, K., & Jenkins, R. (Eds.). (2017). Robot Ethics 2.0: From Autonomous Cars to Artificial Intelligence. Oxford University Press.
• [30] Notomista G., Ve Botsch M., (2016), “A Machıne Learnıng Approach For The Segmentation Of Driving Maneuvers And Its Application In Autonomous Parking”, JAISCR, 2017, Vol. 7, No. 4, pp. 243 – 255.
• [31] Zhang P., Xiong L., Yu Z., Fang P., Yan S., Yao S., Zhou Y., (2019), “Reinforcement Learning-Based End-to-End Parking for Automatic Parking System”, sensors 2019, 19, 3996.
• [32] Lin, P., Abney, K., & Jenkins, R. (Eds.). (2017). Robot Ethics 2.0: From Autonomous Cars to Artificial Intelligence. Oxford University Press.
• [33] Moon J., Bae I., Kim S., (2019), “Automatic Parking Controller with a Twin Artificial Neural Network Architecture”, Hindawi 2019, Article ID 4801985.
• [34] Ayachi, R., Afif, M., Said Y., and Abdelali, A. B, "Traffic Sign Recognition Based On Scaled Convolutional Neural Network For Advanced Driver Assistance System," 2020 IEEE 4th International Conference on Image Processing, Applications and Systems (IPAS), Genova, Italy, 2020, pp. 149-154.